Visual-Based Manufacturing Platform Level Detection Method

This paper proposes a visual-based method for detecting the tilt angles of a platform using a single image. A particular circular reference object is used to provide information of the tilt angles via projective geometry. The image features of the reference object extracted by the basic rectangle and corner detection algorithm are used for ANFIS to estimate the tilt angles. The method is verified by simulation that it can detect the tilt angles very closely. Moreover, the method offers a very easy and low-cost approach for manufacturing appLications.

[1]  Linda G. Shapiro,et al.  Computer Vision , 2001 .

[2]  Martin T. Hagan,et al.  Neural network design , 1995 .

[3]  M.A. Dominguez,et al.  Image processing and automated testing in flexible manufacturing systems , 1998, Proceedings of the 37th SICE Annual Conference. International Session Papers.

[4]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[5]  R.L. Kashyap,et al.  Image interpretation and object recognition in manufacturing , 1991, IEEE Control Systems.

[6]  夏郭賢,et al.  Further Study on Camera Position Estimation from Image by Neural Network , 2013 .

[7]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[8]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[9]  Chun-Chieh Wang,et al.  Further study on camera position estimation from image by ANFIS , 2010, Artificial Life and Robotics.

[10]  Nixon,et al.  Feature Extraction & Image Processing , 2008 .

[11]  J.L. Martin,et al.  Parallel raster image processor for PCB manufacturing , 1994, Proceedings of IECON'94 - 20th Annual Conference of IEEE Industrial Electronics.

[12]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..